Michael Gygli

Results 4 comments of Michael Gygli

We'll do another pass over it. Anyway, the preprocessing is done inefficiently.

Hi @hx173149 Certainly the 3 nets help a bit, but I can't imagine it to be 12%. Using linear SVM instead of fine-tuning should only decrease performance. Have you ever...

That is strange. There was an issue with the initial pycaffe wrapper that the mean was off, see https://github.com/facebook/C3D/pull/59 might be that? What I did to ensure that the output...

I believe the way you read in the mean is wrong (mixed dimension). I had the problem that the mean didn't match in my Pull request to Lasagne Recipes: https://github.com/Lasagne/Recipes/pull/41...